commit skill
Create well-structured git commits from the current working tree. Use when the user says 'commit', 'save my work', 'let's commit this', 'make a commit', or any variation of wanting to commit code to git.
Is the commit skill safe?
Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.
No findings.
Install the commit skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/kklimuk/docx-cli.git /tmp/docx-cli mkdir -p ~/.claude/skills cp -r /tmp/docx-cli/.claude/skills/commit ~/.claude/skills/commit
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
Commit
Create clean, well-structured git commits that tell a coherent story.
Process
1. Assess the Working Tree
Run git status (never -uall) and git diff to understand what changed. Also run git log --oneline -5 to match the repo's existing commit message style.
If there are no changes, say so and stop.
2. Group Changes by Intent
Look at the changed files and mentally group them:
- Feature: new functionality (client + server + tests for the same feature = one commit)
- Fix: bug fixes
- Refactor: structural changes that don't change behavior
- Docs: documentation-only changes (CLAUDE.md, README, comments)
- Test: test-only additions or changes
- Chore: config, dependencies, tooling
Rules for grouping:
- Prefer fewer commits. A feature that touches 15 files is still one commit if it's one logical change.
- Only split when intent is genuinely different. "Add collaborative editing" is one commit even if it touches client, server, DB, and tests. But "add collaborative editing" + "fix unrelated CSS bug" should be two commits.
- For a first commit or large initial build, one commit is fine. Don't artificially split an initial implementation.
- Docs updates that accompany code changes go in the same commit. Only separate docs commits for docs-only changes.
3. Present the Plan
Before committing, show the user:
- How many commits you plan to make
- For each commit: the message and which files are included
- Ask for confirmation
4. Create the Commits
For each commit:
- Stage the specific files with git add ... (never git add -A or git add .)
- Commit with a message using this format:
<type>: <concise description>
<optional body — explain WHY, not WHAT. The diff shows what.>
Co-Authored-By: Claude <noreply@anthropic.com>Types: feat, fix, refactor, docs, test, chore
Message guidelines:
- Subject line under 72 characters
- Use imperative mood ("add", not "added" or "adds")
- The subject should complete the sentence "This commit will..."
- Body is optional — use it for non-obvious context (e.g., "the old approach caused X" or "this unblocks Y")
- Always include the Co-Authored-By trailer
5. Verify
After all commits, run git log --oneline -10 to show the result.
Safety Rules
- Never commit .env, credentials, or secrets. Check staged files for these patterns and warn.
- Never use git add -A or git add . — always stage specific files.
- Never amend a commit unless the user explicitly asks.
- Never force push.
- Never skip hooks (--no-verify).
- If a pre-commit hook fails, fix the issue and create a NEW commit (don't amend). To diagnose, read the pre-commit hook (.husky/pre-commit or .pre-commit-config.yaml) to see what it runs, then run each command individually to find the failure.
What NOT To Do
- Don't write commit messages that describe every file changed. The diff does that.
- Don't split a single feature across 5 commits just because it touches 5 directories.
- Don't use vague messages like "update code" or "fix stuff".
- Don't commit generated files (db/schema.ts, dist/, nodemodules/, pycache__/).
More skills from kklimuk/docx-cli
- Cdocx-cliRead, edit, redline, comment on, and create Microsoft Word .docx files. Use to fill out or edit a Word doc, redline a contract with tracked changes, add/resolve comments, replace text keeping its formatting, restyle headings/fonts, edit tables, or read/extract a .docx as Markdown or text. Also BUILD a new .docx — from Markdown or programmatically (code that outputs a Word report with headings, tables, images). Not for PDF, Google Docs, Excel, PowerPoint, or .doc.
- Asecurity-reviewReview code for security vulnerabilities. Use when the user says 'security review', 'security audit', 'check for vulnerabilities', 'pentest the code', 'OWASP check', or any variation of wanting a security assessment.
- Aweak-agent-testRun the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.